拡張分析における ChatGPT の機能の探索: 5 つのユース ケースの説明!

import pandas as pd

df = pd.read_csv("transactions.csv")
df = df.drop_duplicates()
df.to_csv("transactions_cleaned.csv", index=False)

import nltk
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer

# Load the dataset
data = # load your dataset here

# Define a function to process the user's question
def process_question(question):
    # Tokenize the question
    tokens = word_tokenize(question)
    # Perform lemmatization on the tokens
    lemmatizer = WordNetLemmatizer()
    lemmatized_tokens = [lemmatizer.lemmatize(token) for token in tokens]
    return lemmatized_tokens

# Define a function to extract the relevant information from the dataset
def extract_info(lemmatized_question, data):
    if "total" in lemmatized_question and "revenue" in lemmatized_question:
        total_revenue = data["revenue"].sum()
        return total_revenue

# Process the user's question
question = "What was the total revenue for the company in 2020?"
lemmatized_question = process_question(question)

# Extract the relevant information from the dataset
total_revenue = extract_info(lemmatized_question, data)

# Print the result
print("Total revenue for the company in 2020: ", total_revenue)

from pyod.models.mcd import MCD
import numpy as np

X = np.array(df[['Quantity', 'Price', 'Total']])
clf = MCD()
clf.fit(X)
anomalies = clf.predict(X)

from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split

X = df[['Quantity', 'Total']]
y = df['Price']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

rf = RandomForestRegressor(n_estimators=100, random_state=42)
rf.fit(X_train, y_train)
print("R2 score on test set: {:.2f}".format(rf.score(X_test, y_test)))

import matplotlib.pyplot as plt

revenue_by_customer = df.groupby('Customer ID')['Total'].sum()
revenue_by_customer.plot(kind='bar')
plt.xlabel("Customer ID")
plt.ylabel("Total Revenue")
plt.show()